[Python] Irregular time shifts of output compared to inputs in given time series data sets

I have some time series data with multiple features. The output is shifted (I mean the times at which I have the output values are shifted from the corresponding inputs and irregularly). I have some idea of what the shifts can be but not exact. Is there a way to use Long Short-Term Memory (LSTM) neural networks which can take into account these irregular shifts? Or any pre-processing that can help before training a LSTM model?

Continue reading...